Research software engineer on face recognition

Duration of the contract: 18 months.
Location: INRIA Rhône-Alpes (Grenoble, France)
Salary: 2500 to 3000 € brut (gross) per month

LEAR (Learning and Recognition) is a research team at INRIA’s site in Grenoble in the French Alps, see http://lear.inrialpes.fr. LEAR’s main focus is learning based approaches to visual object recognition and scene interpretation, particularly for object category detection, image retrieval, video indexing and the analysis of humans and their movements.

The research engineer will evaluate and optimize different components for robust face recognition in images and videos that have been developed in the team into a robust and highly efficient set of tools. The components for face detection, feature extraction, metric learning, and recognition, are currently coded partly in Matlab and C, and need to be packaged, optimized, and parallelized where possible.

In a collaboration with a local start-up company you will extensively evaluate the system on public and private data sets, in order to optimize the various design choices of the different components. You will closely collaborate with other team members working on planned (inter-)national projects in which face/person recognition will play an important role.

The ideal candidate

* holds a PhD or engineering degree in Computer Vision and/or Machine Learning
* has proven strong programming and development skills in C(++) and Linux scripting
* has good communication skills in English and French

If interested please provide a cover letter, resume and references to Cordelia.Schmid(at)inria.fr and Jakob.Verbeek(at)inria.fr

Application closes 31 May 2010